On 20/03/2025 16:15, Christophe Lyon wrote:
> r14-7202-gc8ec3e1327cb1e added vld1xN and vst1xN intrinsics and some
> tests on arm, but didn't enable some existing tests.
>
> Since these tests are shared with aarch64, this patch removes the
> 'dg-skip-if "unimplemented" { arm*-*-* }' directives and relies on the
> advsimd-intrinsics.exp driver to define the appropriate flags and
> dg-do-what action. (A previous patch removed 'dg-do run', and this
> patch removes 'dg-options "-O3"' which would override the options
> computed by the test driver)
>
> float16 intrinsics require the neon-fp16 FPU, which is possibly
> enabled by advsimd-intrinsics.exp, so we include them unconditionally
> on aarch64 or if fp16 is enabled on arm.
>
> poly64 intrinsics would require crypto-neon-fp-armv8: the patch
> enables the corresponding tests on aarch64 only, since for arm they
> are already covered by other tests in gcc.target/arm/simd/. For some
> reason, poly64 tests where missing from x2 and x3 tests, so the patch
> adds them as needed.
>
> Tested on aarch64-linux-gnu (no change), arm-linux-gnueabihf (the
> additional tests are executed) and various flavors of arm-none-eabi
> (the additional tests are compiled-only on M-profile, executed on
> A-profile).
>
> gcc/testsuite/
> PR target/71233
> * gcc.target/aarch64/advsimd-intrinsics/vld1x2.c: Enable on arm.
> * gcc.target/aarch64/advsimd-intrinsics/vld1x3.c: Likewise.
> * gcc.target/aarch64/advsimd-intrinsics/vld1x4.c: Likewise.
> * gcc.target/aarch64/advsimd-intrinsics/vst1x2.c: Likewise.
> * gcc.target/aarch64/advsimd-intrinsics/vst1x3.c: Likewise.
> * gcc.target/aarch64/advsimd-intrinsics/vst1x4.c: Likewise.
OK.
R.
> ---
> .../aarch64/advsimd-intrinsics/vld1x2.c | 22 +++++++++++------
> .../aarch64/advsimd-intrinsics/vld1x3.c | 22 +++++++++++------
> .../aarch64/advsimd-intrinsics/vld1x4.c | 24 ++++++++++++-------
> .../aarch64/advsimd-intrinsics/vst1x2.c | 22 +++++++++++------
> .../aarch64/advsimd-intrinsics/vst1x3.c | 22 +++++++++++------
> .../aarch64/advsimd-intrinsics/vst1x4.c | 24 ++++++++++++-------
> 6 files changed, 90 insertions(+), 46 deletions(-)
>
> diff --git a/gcc/testsuite/gcc.target/aarch64/advsimd-intrinsics/vld1x2.c
> b/gcc/testsuite/gcc.target/aarch64/advsimd-intrinsics/vld1x2.c
> index 0892ce79118..a653296b766 100644
> --- a/gcc/testsuite/gcc.target/aarch64/advsimd-intrinsics/vld1x2.c
> +++ b/gcc/testsuite/gcc.target/aarch64/advsimd-intrinsics/vld1x2.c
> @@ -1,7 +1,3 @@
> -/* We haven't implemented these intrinsics for arm yet. */
> -/* { dg-skip-if "unimplemented" { arm*-*-* } } */
> -/* { dg-options "-O3" } */
> -
> #include <arm_neon.h>
> #include "arm-neon-ref.h"
>
> @@ -39,7 +35,6 @@ VARIANT (int32, 2, _s32) \
> VARIANT (int64, 1, _s64) \
> VARIANT (poly8, 8, _p8) \
> VARIANT (poly16, 4, _p16) \
> -VARIANT (float16, 4, _f16) \
> VARIANT (float32, 2, _f32) \
> VARIANT (uint8, 16, q_u8) \
> VARIANT (uint16, 8, q_u16) \
> @@ -51,17 +46,30 @@ VARIANT (int32, 4, q_s32) \
> VARIANT (int64, 2, q_s64) \
> VARIANT (poly8, 16, q_p8) \
> VARIANT (poly16, 8, q_p16) \
> -VARIANT (float16, 8, q_f16) \
> VARIANT (float32, 4, q_f32)
>
> +#if defined (__ARM_FP16_FORMAT_IEEE) \
> + || defined (__ARM_FP16_FORMAT_ALTERNATIVE) \
> + || defined (__aarch64__)
> +#define VARIANTS_F16(VARIANT) \
> + VARIANT (float16, 4, _f16) \
> + VARIANT (float16, 8, q_f16)
> +#else
> +#define VARIANTS_F16(VARIANTS_F16)
> +#endif
> +
> #ifdef __aarch64__
> #define VARIANTS(VARIANT) VARIANTS_1(VARIANT) \
> +VARIANTS_F16(VARIANT) \
> +VARIANT (poly64, 1, _p64) \
> +VARIANT (poly64, 2, q_p64) \
> VARIANT (mfloat8, 8, _mf8) \
> VARIANT (mfloat8, 16, q_mf8) \
> VARIANT (float64, 1, _f64) \
> VARIANT (float64, 2, q_f64)
> #else
> -#define VARIANTS(VARIANT) VARIANTS_1(VARIANT)
> +#define VARIANTS(VARIANT) VARIANTS_1(VARIANT) \
> +VARIANTS_F16(VARIANT)
> #endif
>
> /* Tests of vld1_x2 and vld1q_x2. */
> diff --git a/gcc/testsuite/gcc.target/aarch64/advsimd-intrinsics/vld1x3.c
> b/gcc/testsuite/gcc.target/aarch64/advsimd-intrinsics/vld1x3.c
> index 9465e4aabb6..832ee7538f6 100644
> --- a/gcc/testsuite/gcc.target/aarch64/advsimd-intrinsics/vld1x3.c
> +++ b/gcc/testsuite/gcc.target/aarch64/advsimd-intrinsics/vld1x3.c
> @@ -1,7 +1,3 @@
> -/* We haven't implemented these intrinsics for arm yet. */
> -/* { dg-skip-if "unimplemented" { arm*-*-* } } */
> -/* { dg-options "-O3" } */
> -
> #include <arm_neon.h>
> #include "arm-neon-ref.h"
>
> @@ -40,7 +36,6 @@ VARIANT (int32, 2, _s32) \
> VARIANT (int64, 1, _s64) \
> VARIANT (poly8, 8, _p8) \
> VARIANT (poly16, 4, _p16) \
> -VARIANT (float16, 4, _f16) \
> VARIANT (float32, 2, _f32) \
> VARIANT (uint8, 16, q_u8) \
> VARIANT (uint16, 8, q_u16) \
> @@ -52,17 +47,30 @@ VARIANT (int32, 4, q_s32) \
> VARIANT (int64, 2, q_s64) \
> VARIANT (poly8, 16, q_p8) \
> VARIANT (poly16, 8, q_p16) \
> -VARIANT (float16, 8, q_f16) \
> VARIANT (float32, 4, q_f32)
>
> +#if defined (__ARM_FP16_FORMAT_IEEE) \
> + || defined (__ARM_FP16_FORMAT_ALTERNATIVE) \
> + || defined (__aarch64__)
> +#define VARIANTS_F16(VARIANT) \
> + VARIANT (float16, 4, _f16) \
> + VARIANT (float16, 8, q_f16)
> +#else
> +#define VARIANTS_F16(VARIANTS_F16)
> +#endif
> +
> #ifdef __aarch64__
> #define VARIANTS(VARIANT) VARIANTS_1(VARIANT) \
> +VARIANTS_F16(VARIANT) \
> +VARIANT (poly64, 1, _p64) \
> +VARIANT (poly64, 2, q_p64) \
> VARIANT (mfloat8, 8, _mf8) \
> VARIANT (mfloat8, 16, q_mf8) \
> VARIANT (float64, 1, _f64) \
> VARIANT (float64, 2, q_f64)
> #else
> -#define VARIANTS(VARIANT) VARIANTS_1(VARIANT)
> +#define VARIANTS(VARIANT) VARIANTS_1(VARIANT) \
> +VARIANTS_F16(VARIANT)
> #endif
>
>
> diff --git a/gcc/testsuite/gcc.target/aarch64/advsimd-intrinsics/vld1x4.c
> b/gcc/testsuite/gcc.target/aarch64/advsimd-intrinsics/vld1x4.c
> index a1461fd1af5..e5f55f0b730 100644
> --- a/gcc/testsuite/gcc.target/aarch64/advsimd-intrinsics/vld1x4.c
> +++ b/gcc/testsuite/gcc.target/aarch64/advsimd-intrinsics/vld1x4.c
> @@ -1,7 +1,3 @@
> -/* We haven't implemented these intrinsics for arm yet. */
> -/* { dg-skip-if "unimplemented" { arm*-*-* } } */
> -/* { dg-options "-O3" } */
> -
> #include <stdbool.h>
> #include <arm_neon.h>
> #include "arm-neon-ref.h"
> @@ -42,8 +38,6 @@ VARIANT (int32, 2, _s32) \
> VARIANT (int64, 1, _s64) \
> VARIANT (poly8, 8, _p8) \
> VARIANT (poly16, 4, _p16) \
> -VARIANT (poly64, 1, _p64) \
> -VARIANT (float16, 4, _f16) \
> VARIANT (float32, 2, _f32) \
> VARIANT (uint8, 16, q_u8) \
> VARIANT (uint16, 8, q_u16) \
> @@ -55,18 +49,30 @@ VARIANT (int32, 4, q_s32) \
> VARIANT (int64, 2, q_s64) \
> VARIANT (poly8, 16, q_p8) \
> VARIANT (poly16, 8, q_p16) \
> -VARIANT (poly64, 2, q_p64) \
> -VARIANT (float16, 8, q_f16) \
> VARIANT (float32, 4, q_f32)
>
> +#if defined (__ARM_FP16_FORMAT_IEEE) \
> + || defined (__ARM_FP16_FORMAT_ALTERNATIVE) \
> + || defined (__aarch64__)
> +#define VARIANTS_F16(VARIANT) \
> + VARIANT (float16, 4, _f16) \
> + VARIANT (float16, 8, q_f16)
> +#else
> +#define VARIANTS_F16(VARIANTS_F16)
> +#endif
> +
> #ifdef __aarch64__
> #define VARIANTS(VARIANT) VARIANTS_1(VARIANT) \
> +VARIANTS_F16(VARIANT) \
> +VARIANT (poly64, 1, _p64) \
> +VARIANT (poly64, 2, q_p64) \
> VARIANT (mfloat8, 8, _mf8) \
> VARIANT (mfloat8, 16, q_mf8) \
> VARIANT (float64, 1, _f64) \
> VARIANT (float64, 2, q_f64)
> #else
> -#define VARIANTS(VARIANT) VARIANTS_1(VARIANT)
> +#define VARIANTS(VARIANT) VARIANTS_1(VARIANT) \
> +VARIANTS_F16(VARIANT)
> #endif
>
> /* Tests of vld1_x4 and vld1q_x4. */
> diff --git a/gcc/testsuite/gcc.target/aarch64/advsimd-intrinsics/vst1x2.c
> b/gcc/testsuite/gcc.target/aarch64/advsimd-intrinsics/vst1x2.c
> index 3cf5eb3bd7e..8399290c55f 100644
> --- a/gcc/testsuite/gcc.target/aarch64/advsimd-intrinsics/vst1x2.c
> +++ b/gcc/testsuite/gcc.target/aarch64/advsimd-intrinsics/vst1x2.c
> @@ -1,7 +1,3 @@
> -/* We haven't implemented these intrinsics for arm yet. */
> -/* { dg-skip-if "unimplemented" { arm*-*-* } } */
> -/* { dg-options "-O3" } */
> -
> #include <arm_neon.h>
> #include "arm-neon-ref.h"
>
> @@ -39,7 +35,6 @@ VARIANT (int32, 2, _s32) \
> VARIANT (int64, 1, _s64) \
> VARIANT (poly8, 8, _p8) \
> VARIANT (poly16, 4, _p16) \
> -VARIANT (float16, 4, _f16) \
> VARIANT (float32, 2, _f32) \
> VARIANT (uint8, 16, q_u8) \
> VARIANT (uint16, 8, q_u16) \
> @@ -51,17 +46,30 @@ VARIANT (int32, 4, q_s32) \
> VARIANT (int64, 2, q_s64) \
> VARIANT (poly8, 16, q_p8) \
> VARIANT (poly16, 8, q_p16) \
> -VARIANT (float16, 8, q_f16) \
> VARIANT (float32, 4, q_f32)
>
> +#if defined (__ARM_FP16_FORMAT_IEEE) \
> + || defined (__ARM_FP16_FORMAT_ALTERNATIVE) \
> + || defined (__aarch64__)
> +#define VARIANTS_F16(VARIANT) \
> + VARIANT (float16, 4, _f16) \
> + VARIANT (float16, 8, q_f16)
> +#else
> +#define VARIANTS_F16(VARIANTS_F16)
> +#endif
> +
> #ifdef __aarch64__
> #define VARIANTS(VARIANT) VARIANTS_1(VARIANT) \
> +VARIANTS_F16(VARIANT) \
> +VARIANT (poly64, 1, _p64) \
> +VARIANT (poly64, 2, q_p64) \
> VARIANT (mfloat8, 8, _mf8) \
> VARIANT (mfloat8, 16, q_mf8) \
> VARIANT (float64, 1, _f64) \
> VARIANT (float64, 2, q_f64)
> #else
> -#define VARIANTS(VARIANT) VARIANTS_1(VARIANT)
> +#define VARIANTS(VARIANT) VARIANTS_1(VARIANT) \
> +VARIANTS_F16(VARIANT)
> #endif
>
> /* Tests of vst1_x2 and vst1q_x2. */
> diff --git a/gcc/testsuite/gcc.target/aarch64/advsimd-intrinsics/vst1x3.c
> b/gcc/testsuite/gcc.target/aarch64/advsimd-intrinsics/vst1x3.c
> index c05f8e73e64..e7d9e022bba 100644
> --- a/gcc/testsuite/gcc.target/aarch64/advsimd-intrinsics/vst1x3.c
> +++ b/gcc/testsuite/gcc.target/aarch64/advsimd-intrinsics/vst1x3.c
> @@ -1,7 +1,3 @@
> -/* We haven't implemented these intrinsics for arm yet. */
> -/* { dg-skip-if "unimplemented" { arm*-*-* } } */
> -/* { dg-options "-O3" } */
> -
> #include <arm_neon.h>
> #include "arm-neon-ref.h"
>
> @@ -40,7 +36,6 @@ VARIANT (int32, 2, _s32) \
> VARIANT (int64, 1, _s64) \
> VARIANT (poly8, 8, _p8) \
> VARIANT (poly16, 4, _p16) \
> -VARIANT (float16, 4, _f16) \
> VARIANT (float32, 2, _f32) \
> VARIANT (uint8, 16, q_u8) \
> VARIANT (uint16, 8, q_u16) \
> @@ -52,17 +47,30 @@ VARIANT (int32, 4, q_s32) \
> VARIANT (int64, 2, q_s64) \
> VARIANT (poly8, 16, q_p8) \
> VARIANT (poly16, 8, q_p16) \
> -VARIANT (float16, 8, q_f16) \
> VARIANT (float32, 4, q_f32)
>
> +#if defined (__ARM_FP16_FORMAT_IEEE) \
> + || defined (__ARM_FP16_FORMAT_ALTERNATIVE) \
> + || defined (__aarch64__)
> +#define VARIANTS_F16(VARIANT) \
> + VARIANT (float16, 4, _f16) \
> + VARIANT (float16, 8, q_f16)
> +#else
> +#define VARIANTS_F16(VARIANTS_F16)
> +#endif
> +
> #ifdef __aarch64__
> #define VARIANTS(VARIANT) VARIANTS_1(VARIANT) \
> +VARIANTS_F16(VARIANT) \
> +VARIANT (poly64, 1, _p64) \
> +VARIANT (poly64, 2, q_p64) \
> VARIANT (mfloat8, 8, _mf8) \
> VARIANT (mfloat8, 16, q_mf8) \
> VARIANT (float64, 1, _f64) \
> VARIANT (float64, 2, q_f64)
> #else
> -#define VARIANTS(VARIANT) VARIANTS_1(VARIANT)
> +#define VARIANTS(VARIANT) VARIANTS_1(VARIANT) \
> +VARIANTS_F16(VARIANT)
> #endif
>
> /* Tests of vst1_x3 and vst1q_x3. */
> diff --git a/gcc/testsuite/gcc.target/aarch64/advsimd-intrinsics/vst1x4.c
> b/gcc/testsuite/gcc.target/aarch64/advsimd-intrinsics/vst1x4.c
> index a9867c312cf..83b0567963c 100644
> --- a/gcc/testsuite/gcc.target/aarch64/advsimd-intrinsics/vst1x4.c
> +++ b/gcc/testsuite/gcc.target/aarch64/advsimd-intrinsics/vst1x4.c
> @@ -1,7 +1,3 @@
> -/* We haven't implemented these intrinsics for arm yet. */
> -/* { dg-skip-if "unimplemented" { arm*-*-* } } */
> -/* { dg-options "-O3" } */
> -
> #include <arm_neon.h>
> #include "arm-neon-ref.h"
>
> @@ -41,8 +37,6 @@ VARIANT (int32, 2, _s32) \
> VARIANT (int64, 1, _s64) \
> VARIANT (poly8, 8, _p8) \
> VARIANT (poly16, 4, _p16) \
> -VARIANT (poly64, 1, _p64) \
> -VARIANT (float16, 4, _f16) \
> VARIANT (float32, 2, _f32) \
> VARIANT (uint8, 16, q_u8) \
> VARIANT (uint16, 8, q_u16) \
> @@ -54,18 +48,30 @@ VARIANT (int32, 4, q_s32) \
> VARIANT (int64, 2, q_s64) \
> VARIANT (poly8, 16, q_p8) \
> VARIANT (poly16, 8, q_p16) \
> -VARIANT (poly64, 2, q_p64) \
> -VARIANT (float16, 8, q_f16) \
> VARIANT (float32, 4, q_f32)
>
> +#if defined (__ARM_FP16_FORMAT_IEEE) \
> + || defined (__ARM_FP16_FORMAT_ALTERNATIVE) \
> + || defined (__aarch64__)
> +#define VARIANTS_F16(VARIANT) \
> + VARIANT (float16, 4, _f16) \
> + VARIANT (float16, 8, q_f16)
> +#else
> +#define VARIANTS_F16(VARIANTS_F16)
> +#endif
> +
> #ifdef __aarch64__
> #define VARIANTS(VARIANT) VARIANTS_1(VARIANT) \
> +VARIANTS_F16(VARIANT) \
> +VARIANT (poly64, 1, _p64) \
> +VARIANT (poly64, 2, q_p64) \
> VARIANT (mfloat8, 8, _mf8) \
> VARIANT (mfloat8, 16, q_mf8) \
> VARIANT (float64, 1, _f64) \
> VARIANT (float64, 2, q_f64)
> #else
> -#define VARIANTS(VARIANT) VARIANTS_1(VARIANT)
> +#define VARIANTS(VARIANT) VARIANTS_1(VARIANT) \
> +VARIANTS_F16(VARIANT)
> #endif
>
> /* Tests of vst1_x4 and vst1q_x4. */
